Triple

T24144727
Position Surface form Disambiguated ID Type / Status
Subject Peder Oxe E598345 entity
Predicate positionHeld P8 FINISHED
Object Steward of the Realm of Denmark
The Steward of the Realm of Denmark was a high-ranking noble office functioning as the king’s chief administrator and de facto head of government in the Danish monarchy.
E1619915 NE FINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Steward of the Realm of Denmark | Statement: [Peder Oxe, positionHeld, Steward of the Realm of Denmark]
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Steward of the Realm of Denmark
Triple: [Peder Oxe, positionHeld, Steward of the Realm of Denmark]
Generated description
The Steward of the Realm of Denmark was a high-ranking noble office functioning as the king’s chief administrator and de facto head of government in the Danish monarchy.

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69e288c9e488819093dd1acd91b08b8a completed April 17, 2026, 7:23 p.m.
NER Named-entity recognition batch_69f1e00a37b881909e31f85a667e6d83 completed April 29, 2026, 10:40 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0fad2a3e948190baec7d36cf1b91b1 completed May 22, 2026, 1:11 a.m.
NEDg Description generation batch_6a0fae7556348190bd8ce88f416f5833 completed May 22, 2026, 1:16 a.m.
NED2 Entity disambiguation (via description) batch_6a0faf56f8648190bd2640c852c50a2a completed May 22, 2026, 1:20 a.m.
Created at: April 17, 2026, 11:29 p.m.